Triple

T20259206
Position Surface form Disambiguated ID Type / Status
Subject Yiqun Lisa Yin E498785 entity
Predicate hasEmployer P7 FINISHED
Object NTRU Cryptosystems NE NERFINISHED

How this triple was built (3 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: NTRU Cryptosystems | Statement: [Yiqun Lisa Yin, hasEmployer, NTRU Cryptosystems]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: NTRU Cryptosystems
Context triple: [Yiqun Lisa Yin, hasEmployer, NTRU Cryptosystems]
  • A. Cramer–Shoup cryptosystem
    The Cramer–Shoup cryptosystem is a public-key encryption scheme designed to be secure against adaptive chosen-ciphertext attacks, improving on earlier systems like ElGamal in terms of robustness and security guarantees.
  • B. Massey–Omura cryptosystem
    The Massey–Omura cryptosystem is a public-key encryption scheme based on exponentiation in finite fields that enables secure communication without prior key exchange.
  • C. Damgård–Jurik cryptosystem
    The Damgård–Jurik cryptosystem is a public-key encryption scheme that generalizes the Paillier cryptosystem to support larger message spaces and flexible homomorphic properties.
  • D. Merkle–Hellman knapsack cryptosystem
    The Merkle–Hellman knapsack cryptosystem is an early public-key encryption scheme based on the subset sum (knapsack) problem, historically significant as one of the first practical public-key systems though later found to be insecure.
  • E. Rabin cryptosystem
    The Rabin cryptosystem is a public-key encryption scheme based on the hardness of integer factorization, notable for its provable security equivalence to factoring and its similarity to RSA.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: NTRU Cryptosystems
Target entity description: NTRU Cryptosystems is a cryptography company best known for developing the NTRU public-key cryptosystem, an early and influential lattice-based, post-quantum encryption scheme.
  • A. Cramer–Shoup cryptosystem
    The Cramer–Shoup cryptosystem is a public-key encryption scheme designed to be secure against adaptive chosen-ciphertext attacks, improving on earlier systems like ElGamal in terms of robustness and security guarantees.
  • B. Massey–Omura cryptosystem
    The Massey–Omura cryptosystem is a public-key encryption scheme based on exponentiation in finite fields that enables secure communication without prior key exchange.
  • C. Damgård–Jurik cryptosystem
    The Damgård–Jurik cryptosystem is a public-key encryption scheme that generalizes the Paillier cryptosystem to support larger message spaces and flexible homomorphic properties.
  • D. Merkle–Hellman knapsack cryptosystem
    The Merkle–Hellman knapsack cryptosystem is an early public-key encryption scheme based on the subset sum (knapsack) problem, historically significant as one of the first practical public-key systems though later found to be insecure.
  • E. Rabin cryptosystem
    The Rabin cryptosystem is a public-key encryption scheme based on the hardness of integer factorization, notable for its provable security equivalence to factoring and its similarity to RSA.
  • F. None of above. chosen

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69da6275fa6c8190952924930adee150 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e674c84e848190a6e8956698b84026 completed April 20, 2026, 6:47 p.m.
Created at: April 11, 2026, 11:41 p.m.